In the realm of AI technological advancements, Natural Language Processing (NLP) stands out as a branch dedicated to enhancing machine or system processing of human language tasks. Text classification, a crucial area within NLP, has significantly fortified natural language processing tasks. This study zeroes in on language processing tasks in Bengali, our mother tongue. Notably, there's a dearth of research on Bengali text classification, especially concerning its two linguistic forms: "saint" (Sadhu bhasa) and "common" (Cholito bhasa), with a limited dataset size available. Thus, this study aims to classify Bengali texts based on these two forms, utilizing around 2948 pieces of data gathered from Bengali literature, blogs, and articles. To classify Bengali texts, various supervised machine-learning algorithms have been employed, including MNB, RF, DT, SVM, KNN, and XGB. Before implementing these algorithms, dataset preprocessing techniques were applied, such as primary cleaning, regular expression removal, stopwords removal, digit removal, null value removal, and tokenization. Among all the applied machine learning techniques or classifiers for predicting texts in the two forms—saint and common—SVM achieved the highest output accuracy of 92.33%. Additionally, RF, XGB, MNB, DT, and KNN attained accuracies of 91.87%, 91.20%, 88.04%, 86.68%, and 84.88%, respectively. Ultimately, this study opens up avenues for further research in Bangla language processing, particularly in the realm of text classification.